| C4 |
verify-ppt/c4-c4 |
| SmolLM3 |
1. verify-ppt/smollm3-fineweb-edu |
|
2. verify-ppt/smollm3-dclm |
|
3. verify-ppt/smollm3-pes2o |
|
4. verify-ppt/smollm3-wiki |
|
5. verify-ppt/smollm3-stackexchange |
|
6. verify-ppt/smollm3-infiwebmath |
|
7. verify-ppt/smollm3-finemath |
|
8. verify-ppt/smollm3-stack-v2-Python |
|
9. verify-ppt/smollm3-stack-v2-Java |
|
10. verify-ppt/smollm3-stack-v2-JavaScript |
|
11. verify-ppt/smollm3-stack-v2-C |
|
12. verify-ppt/smollm3-stack-v2-Cpp |
|
13. verify-ppt/smollm3-stack-v2-C-Sharp |
|
14. verify-ppt/smollm3-stack-v2-PHP |
|
15. verify-ppt/smollm3-stack-v2-TypeScript |
|
16. verify-ppt/smollm3-stack-v2-Swift |
|
17. verify-ppt/smollm3-stack-v2-SQL |
|
18. verify-ppt/smollm3-stack-v2-Ruby |
|
19. verify-ppt/smollm3-stack-v2-Markdown |
|
20. verify-ppt/smollm3-stack-v2-HTML |
|
21. verify-ppt/smollm3-stack-v2-Rust |
|
22. verify-ppt/smollm3-stack-v2-Go |
|
23. verify-ppt/smollm3-stack-v2-Shell |
|
24. verify-ppt/smollm3-kaggle |
|
25. verify-ppt/smollm3-github-issues |
| Olmo3 |
verify-ppt/olmo3-dolma3_mix |
| Marin |
1. verify-ppt/marin-dclm_marin |
|
2. verify-ppt/marin-proof-pile-algebraic-stack |
|
3. verify-ppt/marin-proof-pile-arxiv |
|
4. verify-ppt/marin-proof-pile-open-web-math |
|
5. verify-ppt/marin-starcoderdata_ada |
|
6. verify-ppt/marin-starcoderdata_agda |
|
7. verify-ppt/marin-starcoderdata_alloy |
|
8. verify-ppt/marin-starcoderdata_antlr |
|
9. verify-ppt/marin-starcoderdata_applescript |
|
10. verify-ppt/marin-starcoderdata_assembly |
|
11. verify-ppt/marin-starcoderdata_augeas |
|
12. verify-ppt/marin-starcoderdata_awk |
|
13. verify-ppt/marin-starcoderdata_batchfile |
|
14. verify-ppt/marin-starcoderdata_bluespec |
|
15. verify-ppt/marin-starcoderdata_c-sharp |
|
16. verify-ppt/marin-starcoderdata_c |
|
17. verify-ppt/marin-starcoderdata_clojure |
|
18. verify-ppt/marin-starcoderdata_cmake |
|
19. verify-ppt/marin-starcoderdata_coffeescript |
|
20. verify-ppt/marin-starcoderdata_common-lisp |
|
21. verify-ppt/marin-starcoderdata_cpp |
|
22. verify-ppt/marin-starcoderdata_css |
|
23. verify-ppt/marin-starcoderdata_cuda |
|
24. verify-ppt/marin-starcoderdata_dart |
|
25. verify-ppt/marin-starcoderdata_dockerfile |
|
26. verify-ppt/marin-starcoderdata_elixir |
|
27. verify-ppt/marin-starcoderdata_elm |
|
28. verify-ppt/marin-starcoderdata_emacs-lisp |
|
29. verify-ppt/marin-starcoderdata_erlang |
|
30. verify-ppt/marin-starcoderdata_f-sharp |
|
31. verify-ppt/marin-starcoderdata_fortran |
|
32. verify-ppt/marin-starcoderdata_git-commits-cleaned |
|
33. verify-ppt/marin-starcoderdata_github-issues-filtered-structured |
|
34. verify-ppt/marin-starcoderdata_glsl |
|
35. verify-ppt/marin-starcoderdata_go |
|
36. verify-ppt/marin-starcoderdata_groovy |
|
37. verify-ppt/marin-starcoderdata_haskell |
|
38. verify-ppt/marin-starcoderdata_html |
|
39. verify-ppt/marin-starcoderdata_idris |
|
40. verify-ppt/marin-starcoderdata_isabelle |
|
41. verify-ppt/marin-starcoderdata_java-server-pages |
|
42. verify-ppt/marin-starcoderdata_java |
|
43. verify-ppt/marin-starcoderdata_javascript |
|
44. verify-ppt/marin-starcoderdata_json |
|
45. verify-ppt/marin-starcoderdata_julia |
|
46. verify-ppt/marin-starcoderdata_jupyter-scripts-dedup-filtered |
|
47. verify-ppt/marin-starcoderdata_jupyter-structured-clean-dedup |
|
48. verify-ppt/marin-starcoderdata_kotlin |
|
49. verify-ppt/marin-starcoderdata_lean |
|
50. verify-ppt/marin-starcoderdata_literate-agda |
|
51. verify-ppt/marin-starcoderdata_literate-coffeescript |
|
52. verify-ppt/marin-starcoderdata_literate-haskell |
|
53. verify-ppt/marin-starcoderdata_lua |
|
54. verify-ppt/marin-starcoderdata_makefile |
|
55. verify-ppt/marin-starcoderdata_maple |
|
56. verify-ppt/marin-starcoderdata_markdown |
|
57. verify-ppt/marin-starcoderdata_mathematica |
|
58. verify-ppt/marin-starcoderdata_matlab |
|
59. verify-ppt/marin-starcoderdata_ocaml |
|
60. verify-ppt/marin-starcoderdata_pascal |
|
61. verify-ppt/marin-starcoderdata_perl |
|
62. verify-ppt/marin-starcoderdata_php |
|
63. verify-ppt/marin-starcoderdata_powershell |
|
64. verify-ppt/marin-starcoderdata_prolog |
|
65. verify-ppt/marin-starcoderdata_protocol-buffer |
|
66. verify-ppt/marin-starcoderdata_python |
|
67. verify-ppt/marin-starcoderdata_r |
|
68. verify-ppt/marin-starcoderdata_racket |
|
69. verify-ppt/marin-starcoderdata_restructuredtext |
|
70. verify-ppt/marin-starcoderdata_rmarkdown |
|
71. verify-ppt/marin-starcoderdata_ruby |
|
72. verify-ppt/marin-starcoderdata_rust |
|
73. verify-ppt/marin-starcoderdata_sas |
|
74. verify-ppt/marin-starcoderdata_scala |
|
75. verify-ppt/marin-starcoderdata_scheme |
|
76. verify-ppt/marin-starcoderdata_shell |
|
77. verify-ppt/marin-starcoderdata_smalltalk |
|
78. verify-ppt/marin-starcoderdata_solidity |
|
79. verify-ppt/marin-starcoderdata_sparql |
|
80. verify-ppt/marin-starcoderdata_sql |
|
81. verify-ppt/marin-starcoderdata_stan |
|
82. verify-ppt/marin-starcoderdata_standard-ml |
|
83. verify-ppt/marin-starcoderdata_stata |
|
84. verify-ppt/marin-starcoderdata_systemverilog |
|
85. verify-ppt/marin-starcoderdata_tcl |
|
86. verify-ppt/marin-starcoderdata_tcsh |
|
87. verify-ppt/marin-starcoderdata_tex |
|
88. verify-ppt/marin-starcoderdata_thrift |
|
89. verify-ppt/marin-starcoderdata_typescript |
|
90. verify-ppt/marin-starcoderdata_verilog |
|
91. verify-ppt/marin-starcoderdata_vhdl |
|
92. verify-ppt/marin-starcoderdata_visual-basic |
|
93. verify-ppt/marin-starcoderdata_xslt |
|
94. verify-ppt/marin-starcoderdata_yacc |
|
95. verify-ppt/marin-starcoderdata_yaml |
|
96. verify-ppt/marin-starcoderdata_zig |
| FineWeb-Edu |
verify-ppt/finewebedu-finewebedu_30b |
| C4 (100B) |
verify-ppt/c4-c4_65 |
| Marin (100B) |
Use verify-ppt/marin-dclm_marin_103b instead of verify-ppt/marin-dclm_marin. The rest of the datasets remain the same. |